© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 124634
    Prev
    Next
    INDEX
    Explanations

    names like Jasmine and Jaz

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron responds to capitalized proper names (named entities), especially personal names.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    </strong>
    -3.17
     Comuni
    -2.95
    餍
    -2.56
    笕
    -2.55
     Paesi
    -2.53
    _'.$
    -2.45
     作る
    -2.42
    </em>
    -2.42
     cerim
    -2.36
    涷
    -2.36
    POSITIVE LOGITS
    .
    2.97
    Compared
    2.11
    навли
    2.08
    деи
    2.08
    ፨
    2.00
     Your
    1.98
    e
    1.98
    </tfoot>
    1.95
     первые
    1.95
    [
    1.94
    Activations Density 0.003%

    No Known Activations